AI NewsMinimax

The open-source community sped up MiniMax's H3 video model with tools like FastH3 and NVIDIA's Sol-H3, cutting generation times from minutes to seconds on high-end hardware.
MiniMax open-sourced its H3 video model in August, and the community has kept optimizing it. FastH3 distills it to four steps for consumer GPUs; NVIDIA's Sol-H3 renders 15 seconds of 768p video with audio in about 6.6 seconds on an 8-GPU B300 server.
It's a community effort spanning FastVideo, NVIDIA, Alibaba, and independent researchers releasing weights and code in the open. The result: video that used to take minutes now finishes in single-digit seconds on the right hardware.
Key Capabilities:

• FastH3: A four-step distilled version that runs on consumer hardware, including Apple Silicon.
• Sol-H3: NVIDIA's benchmark shows 15 seconds of 768p video with audio in about 6.6 seconds.
• Fully open: Weights, training, and inference code released publicly for VDN, PDD, and Turbo LoRAs.

H3 Reference Turbo Realtime lets creators guide video generation with far more visual control than before.
Reactor introduced H3 Reference Turbo Realtime, the latest model by MiniMax. It streams video with audio and guide generation using up to 9 reference images, giving creators significantly more control than earlier versions.
This pushes real-time, reference-guided video generation further, letting users blend multiple visual inputs into a single coherent stream. It's available today on Reactor for developers to start building with immediately.
Key Capabilities:

• More References: Supports up to 9 reference images at once, far more than typical video models.
• Live Streaming: Generates video with audio in a real-time streaming format, not just static clips.
• Available Now: Live today on Reactor for developers to start building with right away.

 Vercel is offering MiniMax H3 and H3 Max at half price through its AI Gateway until September 13.
Vercel Developers announced MiniMax H3 and H3 Max are now 50% off through their AI Gateway, running through September 13. Developers can call the models directly with a simple generateVideo function.
This makes one of the fastest video generation models on the market even cheaper to experiment with. It lowers the barrier for developers building video features into their apps.
Key Capabilities:

• Half Price: MiniMax H3 and H3 Max cost 50% less through Vercel's AI Gateway until September 13.
• Simple Integration: Developers can call video generation with a single generateVideo function.
• Limited Window: The discount runs for a fixed time, pushing developers to try it now.